<abstract xmlns="http://www.w3.org/1999/xhtml">In this paper we present the latest developments in SMT-RAT, a tool for the automated check of quantifier-free real and integer arithmetic formulas for satisfiability. As a distinguishing feature, SMT-RAT provides a set of solving modules and supports their strategic combination. We describe our CArL library for arithmetic computations, the available modules implemented on top of CArL, and how modules can be combined to satisfiability-modulo-theories (SMT) solvers. Besides the traditional SMT approach, some new modules support also the recently proposed and highly promising model-constructing satisfiability calculus approach.</abstract>

Modular strategic SMT solving with SMT-RAT

<abstract xmlns="http://www.w3.org/1999/xhtml">In this paper we introduce a new, high-quality, dataset of images containing fruits. We also present the results of some numerical experiment for training a neural network to detect fruits. We discuss the reason why we chose to use fruits in this project by proposing a few applications that could use such classifier.</abstract>

Faculty of Mathematics and Computer Science

Faculty of Exact Sciences and Engineering

Fruit recognition from images using deep learning

<abstract xmlns="http://www.w3.org/1999/xhtml">Product Derivation represents one of the main challenges that Software Product Line (SPL) faces. Deriving individual products from shared software assets is a time-consuming and an expensive activity. In this paper, we (1) present an MDE approach for engineering SPL and (2) propose to leverage model-to-model transformations (MMT) and model-to-text (MTT) transformations for supporting both domain engineering and application engineering processes. In this work, we use ATL as a model-to-model transformation language and Acceleo as a model-to-text transformation language.The proposed approach is discussed with e-Health product line applications.</abstract>

On the use of model transformation for the automation of product derivation process in SPL

<abstract xmlns="http://www.w3.org/1999/xhtml">Sentiment classification is the process of exploring sentiments, emotions, ideas and thoughts in the sentences which are expressed by the people. Sentiment classification allows us to judge the sentiments and feelings of the peoples by analyzing their reviews, social media comments etc. about all the aspects. Machine learning techniques and Lexicon based techniques are being mostly used in sentiment classification to predict sentiments from customers reviews and comments. Machine learning techniques includes several learning algorithms to judge the sentiments i.e Navie bayes, support vector machines etc whereas Lexicon Based techniques includes SentiWordnet, Wordnet etc. The main target of this survey is to give nearly full image of sentiment classification techniques. Survey paper provides the comprehensive overview of recent and past research on sentiment classification and provides excellent research queries and approaches for future aspects</abstract>

University Institute of Information Technology

Pir Mehr Ali Shah Arid Agriculture University

Pir Mehr Ali Shah Arid Agriculture University Rawalpindi

A survey on sentiment classification algorithms, challenges and applications

<abstract xmlns="http://www.w3.org/1999/xhtml">Problem generators are practical solutions for generating a set of inputs to specific problems. These inputs are widely used for testing, comparing and optimizing placement algorithms. The problem generator presented in this paper fills the gap in the area of 2D Cutting &amp; Packing as the sum of the area of the small objects is equal to the area of the Large Object and has at least one perfect solution. In this paper, the already proposed Upper Deck algorithm is revisited and used to test the proposed generator outputs. This algorithm bypasses the dead area problem that occurs in most of all well-known strategies of the 2D Single Knapsack Problem where we have a single large rectangle to cover with small, heterogeneous rectangle shapes, whom total area exceeds the large object’s area. The idea of placing the small shapes in a free corner simplifies and speeds the placement algorithm as only the available angles are checked for possible placements, and collision detection only requires the checking of corners and edges of the placed shape. Since the proposed generator output has at least one exact solution, a series of optimization performed on the algorithm is also presented.</abstract>

Exact fit problem generator for cutting and packing, revisiting of the upper deck placement algorithm

<abstract xmlns="http://www.w3.org/1999/xhtml">Following up on our previous study on applying hierarchical clustering algorithms to high energy particle physics, this paper explores the possibilities to use deep learning to generate models capable of processing the clusterization themselves. The technique chosen for training is reinforcement learning, that allows the system to evolve based on interactions between the model and the underlying graph. The result is a model, that by learning on a modest dataset of 10, 000 nodes during 70 epochs can reach 83, 77% precision for hierarchical and 86, 33% for high energy jet physics datasets in predicting the appropriate clusters.</abstract>

Hierarchical clustering with deep Q-learning

<abstract xmlns="http://www.w3.org/1999/xhtml">Several hundreds of thousand humans are diagnosed with brain cancer every year, and the majority dies within the next two years. The chances of survival could be easiest improved by early diagnosis. This is why there is a strong need for reliable algorithms that can detect the presence of gliomas in their early stage. While an automatic tumor detection algorithm can support a mass screening system, the precise segmentation of the tumor can assist medical staff at therapy planning and patient monitoring. This paper presents a random forest based procedure trained to segment gliomas in multispectral volumetric MRI records. Beside the four observed features, the proposed solution uses 100 further features extracted via morphological operations and Gabor wavelet filtering. A neighborhood-based post-processing was designed to regularize and improve the output of the classifier. The proposed algorithm was trained and tested separately with the 54 low-grade and 220 high-grade tumor volumes of the MICCAI BRATS 2016 training database. For both data sets, the achieved accuracy is characterized by an overall mean Dice score > 83%, sensitivity > 85%, and specificity > 98%. The proposed method is likely to detect all gliomas larger than 10 mL.</abstract>

Low and high grade glioma segmentation in multispectral brain MRI data

AHEAD OF PRINT

Volume 15 (2023): Issue 2 (December 2023)

Volume 15 (2023): Issue 1 (August 2023)

Volume 14 (2022): Issue 2 (December 2022)

Volume 14 (2022): Issue 1 (August 2022)

Volume 13 (2021): Issue 2 (December 2021)

Volume 13 (2021): Issue 1 (June 2021)

Volume 12 (2020): Issue 2 (December 2020)

Volume 12 (2020): Issue 1 (July 2020)

Volume 11 (2019): Issue 2 (December 2019)

Volume 11 (2019): Issue 1 (August 2019)

Volume 10 (2018): Issue 2 (December 2018)

Volume 10 (2018): Issue 1 (August 2018)

Volume 9 (2017): Issue 2 (December 2017)

Volume 9 (2017): Issue 1 (July 2017)

Volume 8 (2016): Issue 2 (December 2016)

Volume 8 (2016): Issue 1 (June 2016)

Volume 7 (2015): Issue 2 (December 2015)

Volume 7 (2015): Issue 1 (June 2015)

Volume 6 (2014): Issue 2 (December 2014)

Volume 6 (2014): Issue 1 (June 2014)

Volume 5 (2013): Issue 2 (December 2013)

Volume 5 (2013): Issue 1 (July 2013)

Acta Universitatis Sapientiae, Informatica

Acta Universitatis Sapientiae Informatica publishes peer-reviewed, high-quality original papers and surveys in English, in all areas of Computer Science and allied fields. The papers must be self-contained, including the purpose of the research, the basic definitions, the antecedents of the research, the presentation of the state-of-the-art and novel contributions. The articles must contain sufficient references to give the reader a broad view of the studied subject.  Articles must follow the technical requirements described in the Information for Authors. Please note, that if an article fails to do so, it will be rejected without peer-review.  The corresponding author is responsible for obtaining the permission of coauthors and of the authorities or institutions, if needed, for publication, the Editorial Board is disclaiming any responsibility.  The papers have to be prepared carefully, and must include the relevant keywords. References should be listed alphabetically based on the Instruction for Authors given at the address www.acta.sapientia.ro/acta-info/informatica-main.htm.  Why subscribe and read  The journal publishes papers in all fields of Computer Science, so it can satisfy a lot of interests; the online version is very attractive with the hyperlinks.  Why submit  The issues appear regularly 2 times per year, the waiting time is not too long, the online version contains hyperlinks.  Rejection Rate   56%   Archiving  Sciendo archives the contents of this journal in Portico - digital long-term preservation service of scholarly books, journals and collections.  Plagiarism Policy  The editorial board is participating in a growing community of Similarity Check System's users in order to ensure that the content published is original and trustworthy. Similarity Check is a medium that allows for comprehensive manuscripts screening, aimed to eliminate plagiarism and provide a high standard and quality peer-review process.  Article Processing Charge (APC)  The journal does not have article processing charges (APCs) nor article submission charges. 